公开(公告)号：EP1508893A3

公开(公告)日：2007-09-05

申请号：EP04103502.3

申请日：2004-07-22

Applicant: MICROSOFT CORPORATION

Inventor： Droppo, James G. ,  Deng, Li ,  Acero, Alejandro

IPC: G10L21/02

CPC classification number: G10L21/0208

Abstract: A system and method are provided that accurately estimate noise and that reduce noise in pattern recognition signals. The method and system define a mapping random variable as a function of at least a clean signal random variable and a noise random variable. A model parameter that describes at least one aspect of a distribution of values for the mapping random variable is then determined. Based on the model parameter, an estimate for the clean signal random variable is determined. Under many aspects of the present invention, the mapping random variable is a signal-to-noise ratio variable and the method and system estimate a value for the signal-to-noise ratio variable from the model parameter.

公开(公告)号：EP1688919A1

公开(公告)日：2006-08-09

申请号：EP06100071.7

申请日：2006-01-04

Applicant: MICROSOFT CORPORATION

Inventor： Subramanya, Amarnag ,  Droppo, James G. ,  Zhang, Zhengyou ,  Liu, Zicheng

IPC: G10L21/02 ,  H04R3/00 ,  H04R1/14

CPC classification number: G10L21/0208 ,  G10L2021/02165

Abstract: A method and apparatus classify a portion of an alternative sensor signal as either containing noise or not containing noise. The portions of the alternative sensor signal that are classified as containing noise are not used to estimate a portion of a clean speech signal and the channel response associated with the alternative sensor. The portions of the alternative sensor signal that are classified as not containing noise are used to estimate a portion of a clean speech signal and the channel response associated with the alternative sensor.

Abstract translation: 一种方法和装置归类为噪声要么含有或不含有噪声的备选传感器信号的一部分。 象包含噪声不被用于估计干净语音信号的一部分，并且与所述备选传感器相关联的所述信道响应中的备选传感器信号的部分被分类。 作为不包含噪声被用来估计干净语音信号的一部分，并且与所述备选传感器相关联的所述信道响应中的备选传感器信号的部分被分类。

公开(公告)号：EP1465160A2

公开(公告)日：2004-10-06

申请号：EP04006719.1

申请日：2004-03-19

Applicant: MICROSOFT CORPORATION

Inventor： Acero, Alejandro ,  Deng, Li ,  Droppo, James G.

IPC: G10L21/02

CPC classification number: G10L21/0208

Abstract: A method and apparatus estimate additive noise in a noisy signal using incremental Bayes learning, where a time-varying noise prior distribution is assumed and hyperparameters (mean and variance) are updated recursively using an approximation for posterior computed at the preceding time step. The additive noise in time domain is represented in the log-spectrum or cepstrum domain before applying incremental Bayes learning. The results of both the mean and variance estimates for the noise for each of separate frames are used to perform speech feature enhancement in the same log-spectrum or cepstrum domain.

Abstract translation: 一种方法和装置使用增量贝叶斯学习估计噪声信号中的加性噪声​​，其中假定时变噪声先验分布和超参数（均值和方差）使用在前一时间步长计算的后验近似来递归地更新。 在应用增量贝叶斯学习之前，在对数谱或倒谱域中表示时域中的加性噪声​​。 用于每个单独帧的噪声的均值和方差估计的结果用于在相同的对数谱或倒频谱域中执行语音特征增强。

公开(公告)号：EP1398762A1

公开(公告)日：2004-03-17

申请号：EP03019302.3

申请日：2003-08-26

Applicant: MICROSOFT CORPORATION

Inventor： Acero, Alejandro ,  Deng, Li ,  Droppo, James G.

IPC: G10L21/02

CPC classification number: G10L21/0208 ,  G10L15/20 ,  G10L21/0216

Abstract: A new statistical model describes the corruption of spectral features caused by additive noise. In particular, the model explicitly represents the effect of unknown phase together with the unobserved clean signal and noise. Development of the model has realized three techniques for reducing noise in a noisy signal as a function of the model.

Abstract translation: 噪声输入信号的帧被转换为输入特征向量。 使用等式x = y + ln1-en-y获得噪声减小特征向量，其中y是输入特征向量，n是噪声估计。 计算机可读取的记录介质存储降噪程序中还包括独立权利要求。